EchelonGraph CVE & Exposure MCP Server

Internet-exposure footprint for one CVE from EchelonGraph's KEV-exposure radar: how many internet-facing services (distinct ip:port, returned as exposed_hosts; a machine answering on two ports counts twice) the radar has on record running a version its CVE matcher maps to this CVE, with a country/product breakdown and a ransomware flag. Aggregate and host-redacted; free and keyless. Method: exposure counts are derived from Shodan data. Shodan data is owned by Shodan, which holds its copyright (© Shodan). Every 12 h, when Shodan query credits allow, the radar runs one Shodan query per tracked product, reads up to 100 ip:port services per query, and keeps a service when its banner version matches a CISA-KEV or high-EPSS CVE; a service whose row has not been written or refreshed for 21 days is dropped. The radar only looks for its tracked set of CVEs: for a CVE outside that set the note says NOT ASSESSED (exposure_state not_assessed), and its 0 is not a measurement. last_seen is when EchelonGraph last wrote or refreshed a service's row, not when the service was observed: a port still listed by Shodan InternetDB refreshes it without re-reading the banner, so a patched service can stay counted while its port stays open. A count is therefore a banner-version inference over a sample, not an exploit test and not an internet-wide census. Its structured result's state is not_assessed with measured_at null, since the answer dates no observation; the count is still relayed, labelled, as what the radar holds on record. exposure_state says what the count is: exposed, measured_zero, not_assessed or tracking_unknown; coverage.in_scope is the API's tracked verdict; freshness is null; data is the API's JSON. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true.

Weakness, exploit code, detection checks, affected packages and fixed versions for one CVE, from EchelonGraph's per-CVE enrichment. Returns cwes (each cwe_id with name and source), exploits (each with kind, source_name, source_url, source_published_at (the source's date, null if none), eg_first_seen_at (when EchelonGraph recorded it) and verified_status; at most 10, verified first) with exploits_total, exploits_capped, exploits_by_kind and exploits_by_status, affected_packages (ecosystem, package_name, version_range, fixed_version, fixed_branches), fixed_versions (each fixed version with the vulnerable_range it fixes) and timeline (newest enrichment-history rows, with timeline_total). fixed_branches lists each affected range on record (from introduced ("0" is the first version) to below fixed, or through last_affected, with advisory_id (its OSV record) and source); in the ecosystem's version order, an affected version's fix is the first fixed above it that no range of its row holds (none past a range with no fixed). fixed_version is one range's fix, kept for compatibility, not the fix for every affected range. fixed_branches [] is not a finding that no fix exists. verified_status is the source's label, not a guarantee the exploit works on a given system. An empty exploits list is not evidence that no public exploit exists: it covers only the sources EchelonGraph ingests, and which are polled depends on the deployment. A section the API could not read is named in coverage.sections_failed and left out of data, never relayed as an empty list. Its structured result carries notes, with data, which the first text block holds whole up to 30,000 characters; its coverage names the sections relayed, failed and left out. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true.

How one CVE is fixed, as its sources state it, in one answer. Every text is relayed as stated by its source; EchelonGraph has not tested it. An empty list or a remediation_state of none_in_source or not_parsed is not a finding that no fix exists. Returns fix_status (the API's fix-status rule, as CVE Pulse shows it: state and basis), cisa (for a KEV-listed CVE CISA's required_action, due_date, short_description and notes_urls, verbatim; CISA's required_action is directed at US federal civilian agencies (under BOD 26-04, which replaced BOD 22-01 on 10 June 2026) and is not EchelonGraph's advice.), fixed_branches (each affected package with fixed_branches: every affected range, introduced and fixed or last_affected, and fixed_version, one range's fix), vendor_remediations (each vendor advisory naming the CVE, newest first, at most 20, with remediation_state, remediation_kinds and items, each with kind, source_category, text and url), fix_references (references NVD or the CNA tagged Patch or Mitigation), patches, coverage and failed_sections. kind is the vendor's own category, never read from the text: vendor_fix, workaround, mitigation, no_fix_planned, none_available or other. remediation_state is parsed, none_in_source (none listed for this CVE), not_parsed (that vendor's remediation is not read) or withdrawn. ecosystem, package and version (all three or none, sent in request headers, never in the URL) add installed, the verdict at that version, and fixed_in, the lowest unaffected version above it, or null with fixed_in_reason. A section the API could not read is named in failed_sections, not relayed as empty. A REJECTED CVE answers not_assessed. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, vendor texts are shortened first; kinds, states and URLs are kept.

Summary of EchelonGraph's CVE Pulse feed: summary.total active CVEs, their counts by severity band (summary.critical, summary.high, summary.medium, summary.low), the count with no band (summary.none), and summary.last_updated, the newest modification time among those records. summary.none is not a severity rating of None: it counts the active CVEs with no severity band from any source, that is, CVEs not yet scored, and the answer may carry the same count again as summary.unscored. Whenever summary.none is above zero the note says so, and names those CVEs not yet scored, not CVEs rated None. summary.nvd_critical, summary.nvd_high, summary.nvd_medium, summary.nvd_low and summary.nvd_none count the same active CVEs as summary.total by NVD's CVSS severity label: provenance, never EchelonGraph's severity band. summary.nvd_none is neither a count of CVEs rated None nor the count of CVEs with no severity, which is summary.none. summary.rejected counts the CVE records rejected (withdrawn) by their numbering authority, which summary.total and the other counts above leave out: they are withdrawn records, none of them a vulnerability. poller holds the in-memory counters of the NVD poller of the one API instance that answered, counted since that instance last started and zeroed on every restart: they describe that instance, never the feed's size, intake, reliability or freshness. Whenever the answer carries poller the note says so. Its structured result's state is measured, with freshness.nvd_poll the fleet's last completed NVD poll and its interval, from the answer's nvd_poll (freshness null without one), and data equal to the API's JSON less each poller field (or the whole poller) the note names as left out. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true.

One CVE's record: description, severity, cvss_v3_score, cvss_v4_score and cvss_v4_severity, echelongraph_score, echelongraph_severity and score_confidence, epss_score and epss_percentile, CISA-KEV status (kev_listed, kev_added_date, kev_due_date, kev_ransomware) and, if KEV-listed, CISA's own text relayed verbatim (kev_required_action, not EchelonGraph's advice; kev_short_description; kev_notes_urls), ghsa_id, references, cpe_match (one flat list) and cpe_configurations (NVD's configurations as NVD sent them, with each AND/OR operator; absent where none is stored, which is not a finding that no product is affected), remediation (a capped summary of its fix), published, modified and updated_at; each field only where the record has it. Pass a CVE, EUVD or GHSA ID. echelongraph_score, echelongraph_severity and echelongraph_risk are EchelonGraph's score only when score_assessed is true. With score_assessed false the CVE is NOT YET SCORED, not scored 0: any of those three it carries (0, NONE, 0) is a placeholder, not a rating, and does not mean the CVE is harmless; score_unassessed_reason says why, and the note labels each such CVE NOT YET SCORED. An answer with no score_assessed (an API older than that field) does not say whether the CVE was scored, the note says so, and a 0 there is not a rating either. patch_available is true when EchelonGraph holds, or once held, fix evidence for the CVE; patch_evidence is what it holds now, strongest first. patch_available false means no fix evidence is on record, which is not a finding that no fix exists. freshness is null: this answer carries no poll-completion time. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, each list in the record keeps its first entries, and the note names each list cut with its full length.

One vendor advisory in full, by vendor and the vendor's advisory ID (the vendor and vendor_advisory_id of a vendor advisory row, never its advisory_id, EchelonGraph's internal UUID): title, description, severity, cvss_v3_score, cve_ids and known_cve_ids (those with a record in EchelonGraph's CVE feed), affected_products, remediation, references, vendor_modified_at, and withdrawn_at and withdrawn_reason when the vendor withdrew it. remediations lists each remediation the vendor lists, with kind (the vendor's own category, never read from the text: vendor_fix, workaround, mitigation, no_fix_planned, none_available or other), source_category, text, url and the cve_ids and product_ids it covers; each text is the vendor's, verbatim, untested by EchelonGraph. remediation_state is parsed, none_in_source, not_parsed or withdrawn: none_in_source and not_parsed are not a finding that no fix exists. Each advisory carries vendor_published_at (the vendor's date), our_first_seen_at (when EchelonGraph first recorded it) and withdrawn (true: the vendor rescinded it). Each advisory also carries rejected_cve_ids: the CVE IDs it names whose CVE record was rejected (withdrawn) by its numbering authority, which are not active vulnerabilities. coverage.vendor_window is that vendor's window in what EchelonGraph holds: vendor, advisories, earliest_vendor_published_at, latest_vendor_published_at, held_since (where that window begins) and history_backfill (in_progress or not_started: older advisories not all held yet); null when the windows could not be read or carry none for that vendor. measured_at is our_first_seen_at. Its freshness is null: the answer carries no poll-completion time. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true.

Search or list vendor-published advisories, newest first. A query of 3 or more characters is matched case-insensitively as a substring of each advisory's title, description, vendor name, IDs and affected_products (search_match substring). A query of 1 or 2 characters matches whole words only (search_match word). Filter by vendor (slug), severity band and whether the advisory names any CVE ID. Advisories their vendor withdrew are left out. Returns advisories, each with vendor, vendor_advisory_id, title, severity, cvss_v3_score, cve_ids, summary and affected_products where present, and total, total_capped, limit, offset, search_applied and search_match. A search counts at most 1,000 matches: past that, total is 1000 and total_capped is true, which means 1,000 or more (the note writes 1,000+), never exactly 1,000. Each advisory also carries rejected_cve_ids: the CVE IDs it names whose CVE record was rejected (withdrawn) by its numbering authority, which are not active vulnerabilities. The query is sent in a request header, never in the URL. coverage repeats those beside returned, and gives vendor_windows, each vendor's window in what EchelonGraph holds: vendor, advisories, earliest_vendor_published_at, latest_vendor_published_at, held_since (where that window begins) and history_backfill (in_progress or not_started: older advisories not all held yet). An advisory published before its vendor's held_since may not be held, so no advisory from a vendor is not a finding that it published none. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, each row keeps vendor, vendor_advisory_id, title, severity and cve_ids at least, its strings and lists shortened, or rows are left out and the note gives the offset to call next.

The vendor-published advisories that name one CVE, newest first, at most 20: for each, vendor, vendor_display_name, vendor_advisory_id, title, severity and cvss_v3_score where the vendor gives them. Covers the vendor feeds EchelonGraph polls, for example Microsoft MSRC, Red Hat, Cisco, Palo Alto Networks and GitHub GHSA; an empty answer means none of the advisories EchelonGraph holds names the CVE, not that no vendor published one. Each advisory carries vendor_published_at (the vendor's date), our_first_seen_at (when EchelonGraph first recorded it) and withdrawn (true: the vendor rescinded it). Each advisory also carries rejected_cve_ids: the CVE IDs it names whose CVE record was rejected (withdrawn) by its numbering authority, which are not active vulnerabilities. The answer's cve_rejected is true when the CVE record of the CVE asked for was rejected. Each row has remediation_kinds and remediation_state (not_parsed is not none). coverage gives returned, cap, at_cap (true: there may be more) and cve_year; vendor_windows, each vendor's held window: vendor, advisories, earliest_vendor_published_at, latest_vendor_published_at, held_since (where that window begins) and history_backfill (in_progress or not_started: older advisories not all held yet); and vendors_not_fully_held, the vendors absent from the answer of which EchelonGraph holds none, whose held_since is after 1 January of cve_year or not known, or whose history is still being read, which the note names. An advisory published before its vendor's held_since may not be held, so no advisory from a vendor is not a finding that it published none. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, each row keeps vendor, vendor_advisory_id, title, severity and cve_ids at least, its strings and lists shortened.

Whether a product or package at a given version is affected by known CVEs, from the same matcher as echelongraph.io/am-i-affected. The CPE path takes product (an NVD CPE product token, such as nginx) and version, and returns the CVEs whose NVD CPE match criteria include that product at that version; each match names the vendor NVD asserts (cpe_vendor) and whether it was verified (vendor_unknown). The registry path takes ecosystem (npm, PyPI, Maven and other OSV ecosystem names), package and version, and decides each OSV advisory EchelonGraph holds for that package as affected, not affected or undetermined. count depends on assessed: assessed false means the lookup did not evaluate this component, not_assessed_reason says why, and a count of 0 there is not a finding of not affected. An advisory undecidable at this version is reported as undetermined (undetermined_count, and up to 50 of them in undetermined), never as safe. Each match carries cve_id, kev_listed, ransomware, epss_score, effective_score, effective_severity and score_assessed (false: not yet scored, so echelongraph_score is withheld). A registry match also carries interval, the advisory interval holding it, and fixed_in, the lowest unaffected version above it, or null with fixed_in_reason; a CPE match carries no fixed_in. All four inputs travel in request headers, never in the URL. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, the excluded and undetermined samples keep their first 10 entries, each its cve_id and reason, cve_ids keeps its first 10, and each match keeps cve_id, kev_listed, ransomware, epss_score, effective_score, score_assessed and fixed_in at least. Every CPE match stays in the text; near the cap, a registry list's last matches can leave it, and the note says how many.

Search/list CVEs from EchelonGraph's CVE feed (NVD + MITRE-CNA pre-NVD + CISA-KEV + EPSS + GitHub GHSA, each polled on a schedule). Filter by severity, minimum CVSS, free text, and sort; page with limit and offset. Returns cves, each with cve_id, severity, cvss_v3_score, echelongraph_score and score_assessed (whether EchelonGraph has scored it), epss_score and kev_listed where the record has them, and the list's total, total_counted (false: total is not a count), total_is_lower_bound (true: at least total), search_relaxed, limit and offset. echelongraph_score, echelongraph_severity and echelongraph_risk are EchelonGraph's score only when score_assessed is true. With score_assessed false the CVE is NOT YET SCORED, not scored 0: any of those three it carries (0, NONE, 0) is a placeholder, not a rating, and does not mean the CVE is harmless; score_unassessed_reason says why, and the note labels each such CVE NOT YET SCORED. An answer with no score_assessed (an API older than that field) does not say whether the CVE was scored, the note says so, and a 0 there is not a rating either. patch_available is true when EchelonGraph holds, or once held, fix evidence for the CVE; patch_evidence is what it holds now, strongest first. patch_available false means no fix evidence is on record, which is not a finding that no fix exists. freshness is null: this answer carries no poll-completion time. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, each row keeps at least the fields named above and the first 200 characters of its description (100 on a page too long for that), or rows are left out and the note gives the offset to call next.

One CWE (weakness class) and the CVEs classified under it. Returns cwe_id, name and description (from the MITRE CWE catalog EchelonGraph embeds, version catalog_version), total (the active CVEs in EchelonGraph's feed that an NVD, GitHub or CVE.org record classifies under it, rejected and reserved records left out), and cves, one page of 50: each with cve_id, severity, cvss_v3_score, echelongraph_score, echelongraph_severity, score_assessed, kev_listed, published and a shortened description. order says how the rows are sorted (CISA-KEV-listed first, then EchelonGraph score); an answer without order does not state its order, and the note says so. page is the page served, page_size its size and max_page the last page the API serves: a later page is answered as max_page, so past max_page pages total counts CVEs no page lists. echelongraph_score is EchelonGraph's score only when score_assessed is true; the note labels each row that is NOT YET SCORED. A total of 0 says that no CVE in EchelonGraph's feed is classified under that CWE, not that none exists. Pass cwe_id like CWE-79 (or 79) and an optional page (1-200). Its structured result carries state (measured), measured_at (null), method, coverage (total, returned, page, page_requested, page_size, max_page), freshness (null) and notes, with data equal to the API's JSON; the result's last text block repeats it without data (the first text block) and without the note's sentences (the text block before it), with which notes ends. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true.

How one CVE's EPSS score (FIRST's exploit-prediction probability, 0 to 1, with its percentile) has changed, as EchelonGraph recorded it: points, oldest first, each with at, epss_score, epss_percentile and score_date (FIRST's score date, null where the record does not hold it); current, the record's value now (epss_score, epss_percentile, epss_updated_at); series_kind, always change_only; series_starts_at, when EchelonGraph began recording EPSS changes for any CVE; complete_since, from when the record holds every change; coverage, which FIRST score dates the record holds; history_rows, points_truncated and latest_point_matches_current. Pass a CVE ID like CVE-2023-44487. The series is change-only: a point is a recorded change, and a day without a point is not a recorded value. A daily series interpolated from it holds values EchelonGraph never recorded, so the series is never a daily series. Before series_starts_at nothing was recorded, so a missing point there means not recorded, not unchanged, and the value in force before a CVE's first point is not in the series. Between series_starts_at and complete_since the record misses changes, so a missing point there does not mean unchanged either; only from complete_since on is every change a point. coverage.days_missing and coverage.days_partial name the FIRST score dates the record does not hold, or holds for some CVEs only. latest_point_matches_current false means a change is missing from the series. Its structured result's measured_at is current.epss_updated_at (when EchelonGraph last wrote a changed value, not FIRST's score date), its coverage says which part of the record is complete and which score dates it holds, and its freshness is null. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true.

Aggregate totals from EchelonGraph's internet-exposure radars: kev_exposure, internet-facing services running actively-exploited (CISA-KEV) CVEs, plus the ransomware-linked subset, derived from Shodan data; exposed_databases, unauthenticated data stores and observability UIs, found through Shodan (LeakIX when Shodan query credits run low) and then confirmed by EchelonGraph's own identified check (not a pure read: on Redis it names its client, and on ClickHouse its query is recorded in the server's query log); leaked_credentials, sampled from public GitHub push events; and shadow_ai, services found through Certificate Transparency logs and Shodan and then checked by EchelonGraph's identified probes. Shodan data is owned by Shodan, which holds its copyright (© Shodan). It also gives MCP-server counts: hostnames named like an MCP server in EchelonGraph's own Certificate Transparency feed (no Shodan data), each counted once by its latest verdict from EchelonGraph's identified MCP probe, which never sends tools/call. Service counts are distinct ip:port services, not machines. The result's note, and the outputSchema's description of each radar, label every number by what it counts. Of the shadow_ai numbers, only confirmed_exposed counts exposed services. A kev_exposure.newest_kev CVE whose exposure_state is not_assessed has no measurement in the answer: its 0 is not one. Its structured result's state is not_assessed with measured_at null, since no radar dates what it counts; each count is still relayed as what that radar holds on record. freshness gives each radar's last_run_at where the API serves one; coverage names the radars that answered. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true.

The CVEs CISA has added to its Known Exploited Vulnerabilities (KEV) catalog, newest first, from EchelonGraph's copy of that catalog, which polls CISA's feed every 5 minutes. Each kev row gives cve_id, kev_added_date (CISA's dateAdded), kev_due_date, kev_vendor, kev_product, kev_vuln_name and kev_ransomware (known ransomware-campaign use), EchelonGraph's severity, cvss_v3_score, epss_score, epss_percentile and eg_kev_tier for the CVE, and our_first_seen_kev, when EchelonGraph's poller first recorded the CVE entering the catalog (null where no such record exists). Filter by since and until (YYYY-MM-DD, inclusive, on kev_added_date), ransomware, and vendor (an exact, case-insensitive match on kev_vendor); page with limit (1 to 200, default 50) and cursor, passing back the previous page's next_cursor with the same filters. total counts the CVEs matching the filters; kev_listed_total counts every CVE EchelonGraph holds as KEV-listed, and catalog.catalog_count is CISA's own count in the catalog last fetched, so a gap between the two is entries not yet in EchelonGraph's CVE table, which no page returns. CISA's requiredAction, shortDescription and notes are not in these rows: each CVE's own record carries them, verbatim and labelled as CISA's. Its structured result's measured_at is our last successful fetch of CISA's feed (null when the API does not say), coverage counts the CISA KEV catalog (total, returned, kev_listed_total, catalog_count, limit, has_more) and freshness gives last_successful_fetch_at, catalog_version and date_released. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, each row keeps cve_id, kev_added_date, kev_vendor and kev_ransomware at least, or rows are left out, and next_cursor still continues after the page's last row, not the text's.

Check a dependency list against EchelonGraph's advisory corpus, one verdict per component. For container images and Kubernetes pods, the input is an SBOM of each image, or its purls. Pass purls (package URLs, up to 2,000 distinct, 10,000 with repeats) or sbom (a CycloneDX or SPDX JSON document, up to 5,000,000 characters). This server reads the document's purls; only they are sent to the API, in POST bodies of at most 200, never in a URL; the document itself is not sent on. Run from npm, this server is on your machine; over the hosted endpoint (mcp.echelongraph.io) it is EchelonGraph's, and the document is the request body, accepted up to 6 MiB. data.results holds one row per component sent, in order, with verdict (affected, not_affected, undetermined or not_assessed), not_assessed_reason, cve_ids, matched_package and matched_via (a deb or apk purl's upstream qualifier matches as its source package); each match carries fixed_in (the next unaffected version) or null with fixed_in_reason. data.summary counts the verdicts. not_affected is the only clean verdict: not_assessed (no verdict, as for a deb, apk or rpm purl without a distro qualifier naming its release, which EchelonGraph does not guess) and undetermined are not, and the note counts both. The API allows 1,200 components a minute per caller; on a 429 the tool waits out Retry-After, up to 50 seconds a call, then answers what it has, the rest in data.not_sent_purls, not clean. Input with more than 2,000 distinct purls is refused, not truncated. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, each row keeps index, purl, verdict, not_assessed_reason and cve_ids at least, each match its fixed_in while kept; not_affected rows leave the text first, then not_assessed ones; not_sent_purls keeps its first 10.

Check a project's lockfile or pinned manifest against EchelonGraph's advisory corpus, one verdict per dependency. Pass files: 1 to 20 of filename and content, up to 5,000,000 characters in all. Read: requirements.txt (== and === pins only), go.mod (after replace and exclude), package-lock.json and npm-shrinkwrap.json (v1-v3), Cargo.lock, Gemfile.lock, composer.lock, poetry.lock and gradle.lockfile. package.json, pyproject.toml, Pipfile, Gemfile, Cargo.toml, composer.json and build.gradle hold ranges and are refused, naming the lockfile; go.sum is refused: it lists versions the build does not select. The server reads the files into purls; only the purls are sent to the API, in POST bodies of at most 200, never in a URL; filenames and file contents are not sent on. Run from npm, this server is on your machine; over the hosted endpoint (mcp.echelongraph.io) it is EchelonGraph's, and the files are the request body, up to 6 MiB. data.results holds a row per distinct purl, with verdict (affected, not_affected, undetermined or not_assessed) and cve_ids; each match carries kev_listed, epss_score and fixed_in. not_affected is the only clean verdict. data.not_checked lists the first 2,000 entries not sent (file, line, reason), counting all; not_checked entries are not clean. Refused: over 40,000 lines or 300,000 JSON/TOML values a call, a filename over 1,024 characters. At most 2,000 distinct purls and 50 seconds a call. The API allows 1,200 components a minute per caller; on a 429 it waits out Retry-After within that; a later batch cut off, refused or failed ends the call, the rest in data.not_sent_purls, not clean. Past 30,000 characters of JSON, the first text block holds data cut to fit, and the note says what the cut leaves out and where to read it (TEXT CUT); so is structured data (DATA CUT), unless full: true. Cut, each row keeps index, purl, verdict, not_assessed_reason and cve_ids at least; not_checked its first 20.